---
title: "Design Once, Deploy at Scale: Building a Template-Driven ML Ecosystem"
description: "Meta’s ads ranking ecosystem, processing billions of daily requests, faced a bottleneck where propagating new techniques across a large and fragmented model fleet became harder than the innovation itself. To solve this, they introduced Standard Model Templates (SMT), which standardize model design into a small set of reusable building blocks covering architecture, features, training, and serving. This shifts iteration from per-model to template-level, reducing complexity and enabling multi-model optimization that evaluates techniques across representative models. Over two years, SMT reduced per-model engineering time by 92%, shipped over 5000 technique-model combinations, improved offline model quality by 0.63% at neutral serving capacity, and delivered a 0.86% cumulative online lift covering 70% of models. The approach also provides a structured foundation for agentic ML systems, where agents explore and optimize within bounded template spaces, making automation more effective."
---

# Design Once, Deploy at Scale: Building a Template-Driven ML Ecosystem

[Meta](https://yomu.fyi/company/meta) · Anirudh Agrawal · Nov 18, 2026

**Type:** Problem & solution

## Summary

Meta’s ads ranking ecosystem, processing billions of daily requests, faced a bottleneck where propagating new techniques across a large and fragmented model fleet became harder than the innovation itself. To solve this, they introduced Standard Model Templates (SMT), which standardize model design into a small set of reusable building blocks covering architecture, features, training, and serving. This shifts iteration from per-model to template-level, reducing complexity and enabling multi-model optimization that evaluates techniques across representative models. Over two years, SMT reduced per-model engineering time by 92%, shipped over 5000 technique-model combinations, improved offline model quality by 0.63% at neutral serving capacity, and delivered a 0.86% cumulative online lift covering 70% of models. The approach also provides a structured foundation for agentic ML systems, where agents explore and optimize within bounded template spaces, making automation more effective.

## Context

Meta’s ads ranking ecosystem processes billions of daily requests across diverse products and optimization goals, served by a large number of production models. Fragmentation in architectures, features, and settings created high engineering cost, reliability issues, and low predictability for propagating new techniques.

## Approach / What changed

Standard Model Templates (SMT) standardize model design into a curated set of reusable building blocks covering architecture, features, training, and serving. Multi-model optimization evaluates candidate techniques across representative models, considering aggregate performance and regression rate, then validates on held-out models before integrating into the next template version.

## Takeaways

- SMT reduced per-model engineering time by 92% and shipped over 5000 technique-model combinations across Meta’s ads ranking fleet.
- Multi-model optimization evaluates techniques across representative models, considering both aggregate performance and regression rate before integration.
- SMT provides a structured foundation for agentic ML systems, bounding the search space and enabling more effective automation and exploration.

## FAQ

### What is a Standard Model Template?

A Standard Model Template is an opinionated, minimal model setup built from shared components such as architecture choices, feature logic, training settings, and serving configs. It groups similar models around a standard design, reducing unnecessary diversity while preserving needed flexibility.

### How does multi-model optimization work?

Multi-model optimization evaluates candidate techniques across representative models, searching for configurations that improve aggregate performance while limiting regressions. Techniques that pass validation on held-out models are integrated into the next template version.

### What results did Meta achieve with SMT?

Over two years, SMT reduced per-model engineering time by 92%, shipped over 5000 technique-model combinations, improved offline model quality by 0.63% at neutral serving capacity, and delivered a 0.86% cumulative online lift covering 70% of models.

**Tags:** [Ads](https://yomu.fyi/topic/ads), [Machine Learning](https://yomu.fyi/topic/machine-learning), [Meta](https://yomu.fyi/topic/meta), [MLOps](https://yomu.fyi/topic/mlops), [Ranking](https://yomu.fyi/topic/ranking)

- Source: [Meta](https://engineering.fb.com/2026/11/18/ml-applications/design-once-deploy-at-scale-template-driven-ml-ecosystem)
- Source URL: https://engineering.fb.com/2026/11/18/ml-applications/design-once-deploy-at-scale-template-driven-ml-ecosystem
- Ingested by Yomu: 2026-11-18T18:01:08.695Z

[Read original post](https://engineering.fb.com/2026/11/18/ml-applications/design-once-deploy-at-scale-template-driven-ml-ecosystem)
